Driving log safety analysis method and device

Abstract

The invention discloses a driving log safety analysis method and device, and relates to the technical field of urban rail transit. The method comprises the steps that a target driving log corresponding to a target urban rail transit train is obtained, and the target driving log is collected by a vehicle-mounted system of the target urban rail transit train in the driving process of the target urban rail transit train on a target urban rail transit line in a backup mode; determining a plurality of driving events contained in the target driving log, and performing safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each driving event; determining a prediction result event corresponding to the target urban rail transit train according to the plurality of driving events; and outputting and displaying a plurality of driving events, a safety analysis result corresponding to each driving event and a prediction result event corresponding to the target urban rail transit train.

Description

Technical Field

[0001] This application relates to the technical field of urban rail transit, and particularly to a driving log safety analysis method and device. Background Art

[0002] With the continuous development of the urban rail transit industry, some urban rail transit lines have introduced the interconnection technology, that is, the urban rail transit trains on this line can enter other lines, and at the same time, the trains on other lines can also enter this line, running in the standby mode or sharing the line with CBTC (Communication Based Train Control System), effectively solving the problem of idle resource utilization and optimizing the operation structure of urban rail transit.

[0003] In the standby mode, urban rail transit trains cannot obtain the status of the signal ahead and the protected section in real time, and can only obtain the status of the signal ahead through the standby beacons arranged on the ground at one time. However, after the urban rail transit train passes the standby beacon, it cannot know the status of the signal ahead. When the status of the signal ahead changes, the urban rail transit train may not be able to stop in time and thus a safety accident may occur. In response to this situation, the concept of the validity period of standby mode variables is introduced, and the urban rail transit train is controlled based on the validity period parameter of the standby mode variables to ensure the safe driving of the urban rail transit train in the standby mode.

[0004] However, the validity period parameter of the standby mode variables is not universal among interconnected urban rail transit lines. That is, when an urban rail transit train without the control function of the validity period of standby mode variables runs on an urban rail transit line with the control function of the validity period of standby mode variables, it cannot control the driving of the urban rail transit train based on the validity period of standby mode variables, resulting in safety risks in the driving of urban rail transit trains. Therefore, how to ensure the safe driving of urban rail transit trains without the control function of the validity period of standby mode variables on urban rail transit lines with the control function of the validity period of standby mode variables is crucial. Summary of the Invention

[0005] An embodiment of this application provides a driving log safety analysis method and device, and the main purpose is to ensure the safe driving of urban rail transit trains without the control function of the validity period of standby mode variables on urban rail transit lines with the control function of the validity period of standby mode variables.

[0006] To solve the above technical problems, the embodiment of this application provides the following technical solutions: In a first aspect, this application provides a driving log safety analysis method, and the method includes: Obtain the target train operation log corresponding to the target urban rail transit train, where the target train operation log is the train operation log collected by the on-vehicle system of the target urban rail transit train during the process of the target urban rail transit train running on the target urban rail transit line in the backup mode; Determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event, where the safety analysis result corresponding to the train operation event is used to indicate whether the train operation event brings a safety risk to the operation of the target urban rail transit train; Determine a predicted result event corresponding to the target urban rail transit train according to the multiple train operation events, where the predicted result event is used to indicate whether there is a safety risk for the target urban rail transit train within a future period of time; Output and display the multiple train operation events, the safety analysis result corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether there are operations with safety risks during the process of the target urban rail transit train running on the target urban rail transit line in the backup mode, and whether there is a safety risk for the target urban rail transit train within a future period of time.

[0007] In a second aspect, the present application further provides a train operation log safety analysis device, and the device includes: An acquisition unit, configured to acquire the target train operation log corresponding to the target urban rail transit train, where the target train operation log is the train operation log collected by the on-vehicle system of the target urban rail transit train during the process of the target urban rail transit train running on the target urban rail transit line in the backup mode; A first determination unit, configured to determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event, where the safety analysis result corresponding to the train operation event is used to indicate whether the train operation event brings a safety risk to the operation of the target urban rail transit train; A second determination unit, configured to determine a predicted result event corresponding to the target urban rail transit train according to the multiple train operation events, where the predicted result event is used to indicate whether there is a safety risk for the target urban rail transit train within a future period of time; An output unit, configured to output and display a plurality of the driving events, a safety analysis result corresponding to each driving event, and a predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether an operation with safety risks has been performed during the process of the target urban rail transit train running on the target urban rail transit line in the backup mode, and whether there are safety risks for the target urban rail transit train within a future period of time.

[0008] In a third aspect, an embodiment of the present application provides a storage medium, which includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the driving log safety analysis method described in the first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a driving log safety analysis device, which includes a storage medium; and one or more processors. The storage medium is coupled to the processors, and the processors are configured to execute program instructions stored in the storage medium; when the program instructions run, they execute the driving log safety analysis method described in the first aspect.

[0010] By means of the above technical solutions, the technical solutions provided by the present application at least have the following advantages: The present application provides a driving log safety analysis method and device. After the in-vehicle system of the target urban rail transit train obtains the target driving log corresponding to the target urban rail transit train, the in-vehicle system can determine a plurality of driving events included in the target driving log, perform a safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each driving event, and after determining a predicted result event corresponding to the target urban rail transit train according to the plurality of driving events, output and display the plurality of driving events, the safety analysis result corresponding to each driving event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether an operation with safety risks has been performed during the process of the target urban rail transit train running on the target urban rail transit line in the backup mode, and whether there are safety risks for the target urban rail transit train within a future period of time. When it is determined that there are safety risks for the target urban rail transit train within a future period of time, corresponding emergency solutions are executed according to the plurality of driving events and the predicted result event, thereby ensuring the safe driving of the target urban rail transit train.

[0011] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. In order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specific embodiments of the present application are specifically given. Description of the Drawings

[0012] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become readily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It shows a flowchart of a driving log safety analysis method provided by an embodiment of the present application; Figure 2 It shows a flowchart of another driving log safety analysis method provided by an embodiment of the present application; Figure 3 It shows a block diagram of the composition of a driving log safety analysis device provided by an embodiment of the present application; Figure 4 It shows a block diagram of the composition of another driving log safety analysis device provided by an embodiment of the present application. Detailed Embodiments

[0013] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0014] It should be noted that unless otherwise specified, the technical terms or scientific terms used in the present application should have the ordinary meaning understood by those skilled in the art to which the present application belongs.

[0015] Since the validity period parameter of the backup mode variable is not universal among interconnected urban rail transit lines, that is, when an urban rail transit train without the backup mode variable validity period control function travels on an urban rail transit line with the backup mode variable validity period control function, it is impossible to control the running of the urban rail transit train based on the backup mode variable validity period, resulting in still existing safety risks.

[0016] Therefore, in order to ensure that an urban rail transit train without the backup mode variable validity period control function can run safely on an urban rail transit line with the backup mode variable validity period control function, an embodiment of the present application provides a driving log safety analysis method, as Figure 1 shown, the method includes: 101. Obtain the target driving log corresponding to the target urban rail transit train.

[0017] In the embodiment of the present application, the execution subject in each step is the on-vehicle system of the target urban rail transit train.

[0018] Among them, the target train operation log is the train operation log collected by the on-vehicle system of the target urban rail transit train during the operation of the target urban rail transit line in the backup mode. Among them, the target urban rail transit train is an urban rail transit train without the function of controlling the validity period of backup mode variables, and the target urban rail transit line is an urban rail transit line with the function of controlling the validity period of backup mode variables.

[0019] In order to ensure the safe operation of the target urban rail transit train on the target urban rail transit line, the on-vehicle system of the target urban rail transit train needs to perform a safety analysis on the target train operation log, so it is necessary to first obtain the previously collected target train operation log.

[0020] 102. Determine multiple train operation events included in the target train operation log, and perform a safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event.

[0021] Among them, the multiple train operation events included in the target train operation log are specifically an initial cause event and multiple subsequent events. The initial cause event is that the target urban rail transit train operates in the backup mode on the target urban rail transit line, or the target urban rail transit train crosses the line to the target urban rail transit line and operates in the backup mode. The multiple subsequent events can be: the operator did not notify the backup mode train to stop in advance before the emergency unlocking of the route, the train driver did not comply with the signal display and continued to drive after the unlocking countdown ended, the target urban rail transit train occupied the ALS (emergency unlocking) section - the read advance warning beacon is allowed and the active beacon in front of the signal machine has not been read yet, the target urban rail transit train just occupied the OVERLAP (unlocking trigger section) and stopped before reaching the stop point and the OVERLAP in front of the train was unlocked after the countdown ended, the train driver did not comply with the signal display and continued to drive after the OVERLAP unlocking countdown ended, etc. Among them, the safety analysis result corresponding to the train operation event is used to indicate whether the train operation event brings a safety risk to the operation of the target urban rail transit train. After the on-vehicle system obtains the target train operation log corresponding to the target urban rail transit train, it is necessary to determine multiple train operation events included in the target train operation log, and perform a safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event, that is, perform a safety analysis on the multiple subsequent events to obtain the safety analysis result corresponding to each subsequent event. Among them, for any one of the subsequent events, the corresponding safety analysis result is that there is a safety risk and the event executor, or there is no safety risk.

[0022] 103. Determine the predicted result event corresponding to the target urban rail transit train according to the multiple train operation events.

[0023] Among them, the predicted result event corresponding to the target urban rail transit train is used to indicate whether there is a safety risk for the target urban rail transit train in a future period of time, and it can be: (1) When the target urban rail transit train enters an unlocked route and the switch is rotating, the target urban rail transit train runs above and derails due to switch squeezing; (2) The target urban rail transit train enters an area of an unlatched switch and derails due to switch squeezing; (3) There is no safety impact, and the ATP (Automatic Train Protection System) curve can retract to in front of the signal; (4) The train driver obeys the signal display and stops in front of the signal, and there is no safety impact; (5) When the ATP curve of the target urban rail transit train is at the OVERLAP end point, even if it crosses the signal before unlocking, there is no safety impact; (6) The target urban rail transit train remains stationary in place and there is no safety risk, etc.

[0024] After the on-vehicle system obtains the safety analysis results corresponding to each train operation event, it is also necessary to predict the train operation result of the target urban rail transit train, that is, to determine the predicted result event corresponding to the target urban rail transit train according to multiple train operation events.

[0025] 104. Output and display multiple train operation events, the safety analysis results corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train.

[0026] After the on-vehicle system determines the predicted result event corresponding to the target urban rail transit train, it is necessary to output and display multiple train operation events, the safety analysis results corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether there are operations with safety risks during the process of the target urban rail transit train running on the target urban rail transit line in the standby mode, and whether there is a safety risk for the target urban rail transit train in a future period of time. When it is determined that there is a safety risk for the target urban rail transit train in a future period of time, corresponding emergency solutions are executed according to multiple train operation events and predicted result events, so as to ensure the safe operation of the target urban rail transit train.

[0027] An embodiment of the present application provides a method for safety analysis of train operation logs. After the on-vehicle system of a target urban rail transit train obtains the target train operation log corresponding to the target urban rail transit train, the on-vehicle system can determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event. After determining the predicted result event corresponding to the target urban rail transit train based on the multiple train operation events, the method outputs and displays the multiple train operation events, the safety analysis result corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether there are any operations with safety risks during the process of the target urban rail transit train running in the target urban rail transit line in the backup mode, and whether there are safety risks for the target urban rail transit train in a future period of time. When it is determined that there are safety risks for the target urban rail transit train in a future period of time, corresponding emergency resolution measures are executed according to the multiple train operation events and the predicted result event, thereby ensuring the safe operation of the target urban rail transit train.

[0028] For more detailed description, an embodiment of the present application provides another method for safety analysis of train operation logs, as Figure 2 shown. The method includes: 201. Train a deep learning model based on a training sample set to obtain a safety analysis model.

[0029] In order to ensure that after the on-vehicle system obtains the target train operation log corresponding to the target urban rail transit train, it can accurately determine the safety analysis result corresponding to each train operation event included in the target train operation log, it is necessary to pre-train a safety analysis model. The following will detail how to train and obtain a safety analysis model.

[0030] (1) Obtain a training sample set, where the training sample set contains multiple training samples. For any one training sample, it includes a sample train operation log, the initial cause event included in the sample train operation log, multiple subsequent events, and the safety analysis result corresponding to each subsequent event.

[0031] (2) Train the deep learning model based on the training sample set until the loss function corresponding to the deep learning model converges to obtain a safety analysis model.

[0032] Among them, the deep learning model can be a model established according to any existing deep learning algorithm, and the embodiment of the present application does not specifically limit this.

[0033] Iteratively train a deep learning model based on a training sample set containing multiple training samples; among them, after each round of training, determine whether the loss function of the deep learning model converges; if the loss function converges, determine the deep learning model obtained after this round of training as the safety analysis model; if the loss function does not converge, optimize and adjust the model parameters of the deep learning model according to the loss function, and enter the next round of training based on the optimized and adjusted deep learning model.

[0034] That is, after multiple rounds of iterative training of the deep learning model based on the training sample set, when the loss function of the deep learning model converges, determine the deep learning model at this time as the safety analysis model.

[0035] Since, in some specific cases, even if a large number of iterative trainings are performed, the loss function of the deep learning model will not converge. Therefore, in order to avoid the endless iterative training of the deep learning model, when it is determined that the loss function of the deep learning model obtained after this round of training does not converge, the following two methods can be but are not limited to be used for processing: 1. If the loss function of the deep learning model does not converge, determine whether the current cumulative iterative training duration of iteratively training the deep learning model based on the training sample set reaches a preset duration threshold.

[0036] If the current cumulative iterative training duration reaches the preset duration threshold, it means that the iterative training duration has reached the requirement. At this time, the iterative training can be stopped, and the deep learning model obtained after this round of training can be determined as the safety analysis model.

[0037] If the current cumulative iterative training duration does not reach the preset duration threshold, the steps of optimizing and adjusting the model parameters of the deep learning model according to the loss function and entering the next round of training based on the optimized and adjusted deep learning model can be entered.

[0038] 2. If the loss function of the deep learning model does not converge, determine whether the current cumulative iterative training times of iteratively training the deep learning model based on the training sample set reaches a preset number threshold.

[0039] If the current cumulative iterative training times reach the preset number threshold, it means that the iterative training times have reached the requirement. At this time, the iterative training can be stopped, and the deep learning model obtained after this round of training can be determined as the safety analysis model.

[0040] If the current cumulative iterative training times do not reach the preset number threshold, the steps of optimizing and adjusting the model parameters of the deep learning model according to the loss function and entering the next round of training based on the optimized and adjusted deep learning model can be entered.

[0041] 202. Obtain the target train operation log corresponding to the target urban rail transit train.

[0042] Among them, regarding step 202 of obtaining the target train operation log corresponding to the target urban rail transit train, reference can be made to the relevant description of step 101 above, and the embodiments of the present application will not elaborate here.

[0043] 203. Determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event.

[0044] After the on-vehicle system obtains the target train operation log corresponding to the target urban rail transit train, it is necessary to determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event, that is, perform safety analysis on multiple subsequent events to obtain the safety analysis result corresponding to each subsequent event.

[0045] Specifically, in this step, the on-vehicle system can use any one of the following two methods to determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event: (1) First, extract multiple train operation events from the target train operation log according to the first preset rule, where the first preset rule is used to indicate how to extract train operation events from the train operation log, and the multiple train operation events include the initial cause event and multiple subsequent events; secondly, perform safety analysis on the multiple subsequent events according to the preset rule set and the initial cause event to obtain the safety analysis result corresponding to each subsequent event, where the preset rule set includes multiple second preset rules, and the multiple second preset rules are used to determine whether each subsequent event brings safety risks to the operation of the target urban rail transit train and the event executor corresponding to each subsequent event. For any subsequent event, its corresponding safety analysis result is that there is a safety risk and an event executor, or there is no safety risk.

[0046] (2) Input the target train operation log into the safety analysis model, so that the safety analysis model extracts multiple train operation events (i.e., the initial cause event and multiple subsequent events) from the target train operation log, determines the safety analysis result corresponding to each subsequent event according to the initial cause event and the multiple subsequent events, and outputs the initial cause event, the multiple subsequent events, and the safety analysis result corresponding to each subsequent event, where for any subsequent event, its corresponding safety analysis result is that there is a safety risk and an event executor, or there is no safety risk.

[0047] 204. Determine the predicted result event corresponding to the target urban rail transit train according to the multiple train operation events.

[0048] After the vehicle-mounted system obtains the safety analysis results corresponding to each driving event, it is also necessary to predict the driving results of the target urban rail transit train, that is, to determine the predicted result event corresponding to the target urban rail transit train according to multiple driving events. The specific process is as follows: First, obtain the first data table, where the first data table records multiple first driving event sets and the result events corresponding to each first driving event set. For any first driving event set, it contains multiple driving events. Second, match the multiple driving events included in the target driving log with the multiple driving events included in each first driving event set respectively, and determine the result event corresponding to the first driving event set with successful matching as the predicted result event corresponding to the target urban rail transit train.

[0049] Further, in the embodiment of the present application, after the vehicle-mounted system determines the predicted result event corresponding to the target urban rail transit train, when it is determined that there is a safety risk in the predicted result event corresponding to the target urban rail transit train, it can first obtain the second data table, where the second data table records multiple second driving event sets and the corresponding solutions for each second driving event set. For any second driving event set, it contains multiple driving events, and the corresponding result event has a safety risk. Second, match the multiple driving events included in the target driving log with the multiple driving events included in each second driving event set respectively, and determine the solution corresponding to the second driving event set with successful matching as the solution corresponding to the target urban rail transit train.

[0050] 205. Output and display multiple driving events, the safety analysis results corresponding to each driving event, the predicted result event corresponding to the target urban rail transit train, and the solution.

[0051] After the vehicle-mounted system determines the predicted result event and the solution corresponding to the target urban rail transit train, it is necessary to output and display multiple driving events, the safety analysis results corresponding to each driving event, the predicted result event corresponding to the target urban rail transit train, and the solution, so that the train driver of the target urban rail transit train can know whether the target urban rail transit train has performed operations with safety risks during the process of driving on the target urban rail transit line in the backup mode, whether there are safety risks for the target urban rail transit train in the next period of time, and the corresponding solutions when there are safety risks for the target urban rail transit train in the next period of time. Thus, the train driver can execute corresponding emergency solutions according to multiple driving events, predicted result events, and solutions, so as to ensure the safe driving of the target urban rail transit train.

[0052] Further, in the embodiment of the present application, when it is determined that there is no safety risk in the predicted result event corresponding to the target urban rail transit train, and the safety analysis results corresponding to one or more train operation events indicate that there is a safety risk, the on-vehicle system may further send the multiple train operation events and the safety analysis results corresponding to each train operation event to the target terminal device, where the target terminal device is the terminal device of the event executor corresponding to the train operation event with a safety risk; when the target terminal device receives the multiple train operation events and the safety analysis results corresponding to each train operation event sent to the target terminal device, it is required to output and display the multiple train operation events and the safety analysis results corresponding to each train operation event, so as to prompt the user of the target terminal device to avoid performing operations with safety risks again during subsequent train operation, thereby ensuring the safe train operation of the target urban rail transit train.

[0053] Further, as an implementation of the above Figure 1 and Figure 2 method shown, another embodiment of the present application further provides a train operation log safety analysis device. The device embodiment corresponds to the foregoing method embodiment. For the convenience of reading, the details of the foregoing method embodiment will not be described one by one in this device embodiment, but it should be clear that the device in this embodiment can correspondingly implement all the contents of the foregoing method embodiment. This device is applied to ensure the safe train operation of an urban rail transit train without the validity period control function of the backup mode variable on an urban rail transit line with the validity period control function of the backup mode variable. Specifically, as Figure 3 shown, the device includes: An acquisition unit 31, configured to acquire a target train operation log corresponding to the target urban rail transit train, where the target train operation log is the train operation log collected by the on-vehicle system of the target urban rail transit train during the driving process on the target urban rail transit line in the backup mode; A first determination unit 32, configured to determine multiple train operation events included in the target train operation log, and perform a safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event, where the safety analysis result corresponding to the train operation event is used to indicate whether the train operation event brings a safety risk to the train operation of the target urban rail transit train; A second determination unit 33, configured to determine a predicted result event corresponding to the target urban rail transit train according to the multiple train operation events, where the predicted result event is used to indicate whether there is a safety risk for the target urban rail transit train in a future period of time; An output unit 34 for outputting and displaying a plurality of the driving events, the safety analysis result corresponding to each driving event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether any operation with safety risks has been performed during the process of the target urban rail transit train running in the target urban rail transit line in the backup mode, and whether there are safety risks for the target urban rail transit train in a future period of time.

[0054] Further, as Figure 4 shown, the first determination unit 32 is specifically configured to: extract a plurality of the driving events from the target driving log according to a first preset rule, where the plurality of driving events include a primary cause event and a plurality of subsequent events; perform a safety analysis on the plurality of subsequent events according to a preset rule set and the primary cause event to obtain a safety analysis result corresponding to each subsequent event, where the preset rule set includes a plurality of second preset rules, and for any one subsequent event, its corresponding safety analysis result is that there is a safety risk and the event executor, or there is no safety risk.

[0055] Further, as Figure 4 shown, the first determination unit 32 is specifically configured to: input the target driving log into a safety analysis model, so that the safety analysis model extracts a primary cause event and a plurality of subsequent events from the target driving log, determines a safety analysis result corresponding to each subsequent event according to the primary cause event and the plurality of subsequent events, and outputs the primary cause event, the plurality of subsequent events, and the safety analysis result corresponding to each subsequent event, where for any one subsequent event, its corresponding safety analysis result is that there is a safety risk and the event executor, or there is no safety risk.

[0056] Further, as Figure 4 shown, the device further includes: A training unit 35 for obtaining a training sample set, where the training sample set includes a plurality of training samples, and for any one training sample, it includes a sample driving log, the primary cause event included in the sample driving log, a plurality of subsequent events, and the safety analysis result corresponding to each subsequent event; iteratively train a deep learning model based on the training sample set; where after each round of training, determine whether the loss function of the deep learning model converges; if the loss function converges, determine the deep learning model obtained after this round of training as the safety analysis model; If the loss function does not converge, the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the next round of training is entered based on the optimized deep learning model.

[0057] Further, as Figure 4 shown, the second determination unit 33 includes: Obtain a first data table, where multiple first train operation event sets and result events corresponding to each of the first train operation event sets are recorded in the first data table; Match the multiple train operation events included in the target train operation log with the multiple train operation events included in each of the first train operation event sets; Determine the result event corresponding to the first train operation event set with which the match is successful as the predicted result event corresponding to the target urban rail transit train.

[0058] Further, as Figure 4 shown, the device further includes: A third determination unit 36, configured to obtain a second data table, where multiple second train operation event sets and solutions corresponding to each of the second train operation event sets are recorded in the second data table; Match the multiple train operation events included in the target train operation log with the multiple train operation events included in each of the second train operation event sets; Determine the solution corresponding to the second train operation event set with which the match is successful as the solution corresponding to the target urban rail transit train; The output unit 34 is specifically configured to: output and display multiple train operation events, safety analysis results corresponding to each train operation event, predicted result events corresponding to the target urban rail transit train, and solutions.

[0059] Further, as Figure 4 shown, the device further includes: A sending unit 37, configured to send multiple train operation events and safety analysis results corresponding to each train operation event to a target terminal device, so that the target terminal device outputs and displays multiple train operation events and safety analysis results corresponding to each train operation event.

[0060] An embodiment of the present application provides a method and device for safety analysis of train operation logs. After the on-vehicle system of a target urban rail transit train obtains the target train operation log corresponding to the target urban rail transit train, the on-vehicle system can determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain the safety analysis result corresponding to each train operation event. After determining the predicted result event corresponding to the target urban rail transit train according to the multiple train operation events, the multiple train operation events, the safety analysis result corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train are output and displayed, so that the train driver of the target urban rail transit train can know whether there are any operations with safety risks during the process of the target urban rail transit train running in the target urban rail transit line in the backup mode, and whether there are safety risks for the target urban rail transit train in a future period of time. When it is determined that there are safety risks for the target urban rail transit train in a future period of time, corresponding emergency solutions are executed according to the multiple train operation events and the predicted result event, thereby ensuring the safe operation of the target urban rail transit train.

[0061] An embodiment of the present application provides a storage medium. The storage medium includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the above-mentioned method for safety analysis of train operation logs. The storage medium may include non-permanent memory in a computer-readable medium, forms such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0062] An embodiment of the present application further provides a device for safety analysis of train operation logs. The device includes a storage medium; and one or more processors. The storage medium is coupled to the processor, and the processor is configured to execute program instructions stored in the storage medium; when the program instructions run, they execute the above-mentioned method for safety analysis of train operation logs.

[0063] An embodiment of the present application provides a device. The device includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: Obtain the target train operation log corresponding to the target urban rail transit train, where the target train operation log is the train operation log collected by the on-vehicle system of the target urban rail transit train during the process of the target urban rail transit train running in the target urban rail transit line in the backup mode; Determine multiple train operation events included in the target train operation log, and perform safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event, where the safety analysis result corresponding to the train operation event is used to indicate whether the train operation event brings a safety risk to the operation of the target urban rail transit train; Determine a predicted result event corresponding to the target urban rail transit train according to the multiple train operation events, where the predicted result event is used to indicate whether there is a safety risk for the target urban rail transit train in a future period of time; Output and display the multiple train operation events, the safety analysis result corresponding to each train operation event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether there has been an operation with a safety risk during the operation of the target urban rail transit train in the target urban rail transit line in the backup mode, and whether there is a safety risk for the target urban rail transit train in a future period of time.

[0064] Further, the determining multiple train operation events included in the target train operation log and performing safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event includes: Extract multiple train operation events from the target train operation log according to a first preset rule, where the multiple train operation events include a primary cause event and multiple subsequent events; Perform safety analysis on the multiple subsequent events according to a preset rule set and the primary cause event to obtain a safety analysis result corresponding to each subsequent event, where the preset rule set includes multiple second preset rules, and for any subsequent event, its corresponding safety analysis result is that there is a safety risk and the event executor, or there is no safety risk.

[0065] Further, the determining multiple train operation events included in the target train operation log and performing safety analysis on the multiple train operation events to obtain a safety analysis result corresponding to each train operation event includes: Input the target train operation log into a safety analysis model, so that the safety analysis model extracts a primary cause event and multiple subsequent events from the target train operation log, determines a safety analysis result corresponding to each subsequent event according to the primary cause event and the multiple subsequent events, and outputs the primary cause event, the multiple subsequent events, and the safety analysis result corresponding to each subsequent event, where for any subsequent event, its corresponding safety analysis result is that there is a safety risk and the event executor, or there is no safety risk.

[0066] Further, the method further includes: Obtain a training sample set, where the training sample set contains multiple training samples. For any one training sample, it includes a sample driving log, the initial cause event included in the sample driving log, multiple subsequent events, and the safety analysis result corresponding to each subsequent event; Iteratively train a deep learning model based on the training sample set; where After each round of training, determine whether the loss function of the deep learning model converges; If the loss function converges, determine the deep learning model obtained after this round of training as the safety analysis model; If the loss function does not converge, optimize and adjust the model parameters of the deep learning model according to the loss function, and enter the next round of training based on the optimized and adjusted deep learning model.

[0067] Further, determining the predicted result event corresponding to the target urban rail transit train according to the multiple driving events includes: Obtain a first data table, where the first data table records multiple first driving event sets and the result event corresponding to each first driving event set; Match the multiple driving events included in the target driving log with the multiple driving events included in each first driving event set respectively; Determine the result event corresponding to the first driving event set with successful matching as the predicted result event corresponding to the target urban rail transit train.

[0068] Further, the method further includes: Obtain a second data table, where the second data table records multiple second driving event sets and the solution corresponding to each second driving event set; Match the multiple driving events included in the target driving log with the multiple driving events included in each second driving event set respectively; Determine the solution corresponding to the second driving event set with successful matching as the solution corresponding to the target urban rail transit train; The outputting and displaying multiple driving events, the safety analysis result corresponding to each driving event, and the predicted result event corresponding to the target urban rail transit train includes: Output and display multiple driving events, the safety analysis result corresponding to each driving event, the predicted result event corresponding to the target urban rail transit train, and the solution.

[0069] Further, the method further includes: Send multiple of the driving events and the safety analysis results corresponding to each driving event to a target terminal device, so that the target terminal device outputs and displays the multiple driving events and the safety analysis results corresponding to each driving event.

[0070] This application also provides a computer program product. When executed on a data processing device, it is adapted to execute program code initialized with the following method steps: Obtain a target driving log corresponding to a target urban rail transit train, where the target driving log is a driving log collected by the on-vehicle system of the target urban rail transit train during the process of the target urban rail transit train running on a target urban rail transit line in a backup mode; Determine multiple driving events included in the target driving log, and perform a safety analysis on the multiple driving events to obtain a safety analysis result corresponding to each driving event, where the safety analysis result corresponding to the driving event is used to indicate whether the driving event brings a safety risk to the driving of the target urban rail transit train; Determine a predicted result event corresponding to the target urban rail transit train according to the multiple driving events, where the predicted result event is used to indicate whether there is a safety risk for the target urban rail transit train within a future period of time; Output and display the multiple driving events, the safety analysis results corresponding to each driving event, and the predicted result event corresponding to the target urban rail transit train, so that the train driver of the target urban rail transit train can know whether there has been an operation with a safety risk during the process of the target urban rail transit train running on the target urban rail transit line in a backup mode, and whether there is a safety risk for the target urban rail transit train within a future period of time.

[0071] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0073] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0075] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0076] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash RAM. The memory is an example of computer-readable media.

[0077] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0078] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0079] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0080] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A driving log safety analysis method, characterized in that: The method comprises: Obtaining a target driving log corresponding to a target city rail transit train, wherein the target driving log is a driving log collected by an onboard system of the target city rail transit train when the target city rail transit train is traveling on the target city rail transit line in a backup mode; Determine a plurality of driving events included in the target driving log, and perform safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each driving event, wherein the safety analysis result corresponding to the driving event is used to indicate whether the driving event brings safety risks to the driving of the target urban rail transit train; Determine a prediction result event corresponding to the target urban rail transit train according to the plurality of driving events, wherein the prediction result event is used to indicate whether the target urban rail transit train has a safety risk in the future; The output displays multiple driving events, the safety analysis results corresponding to each driving event, and the predicted result events corresponding to the target city rail transit train, so that the train driver of the target city rail transit train can know whether the target city rail transit train has performed operations with safety risks while driving on the target city rail transit line in a backup mode, and whether the target city rail transit train will have safety risks in the future.

2. The method according to claim 1, characterized in that The determining of a plurality of driving events included in the target driving log, and performing safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each driving event, includes: Extracting a plurality of driving events from the target driving log according to a first preset rule, wherein the plurality of driving events include an initial event and a plurality of subsequent events; A security analysis is performed on the multiple subsequent events according to the preset rule set and the initial cause event to obtain a security analysis result corresponding to each subsequent event, wherein the preset rule set includes multiple second preset rules, and for any subsequent event, the corresponding security analysis result is the existence of a security risk and an event executor, or the absence of a security risk.

3. The method according to claim 1, characterized in that The determining of a plurality of driving events included in the target driving log, and performing safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each driving event, includes: The target driving log is input into the safety analysis model so that the safety analysis model can extract the initial cause event and multiple subsequent events from the target driving log, and determine the safety analysis result corresponding to each subsequent event based on the initial cause event and the multiple subsequent events, and output the initial cause event, the multiple subsequent events and the safety analysis result corresponding to each subsequent event, wherein, for any subsequent event, the corresponding safety analysis result is the existence of a safety risk and an event executor, or the absence of a safety risk.

4. The method according to claim 3, characterized in that The method further comprises: Obtaining a training sample set, wherein the training sample set includes a plurality of training samples, and for any training sample, it includes a sample driving log, an initial event included in the sample driving log, a plurality of subsequent events, and a safety analysis result corresponding to each of the subsequent events; The deep learning model is iteratively trained based on the training sample set; wherein, After each round of training, determining whether the loss function of the deep learning model converges; If the loss function converges, the deep learning model obtained after this round of training is determined as the security analysis model; If the loss function does not converge, the model parameters of the deep learning model are optimized and adjusted according to the loss function, and the next round of training is entered based on the optimized and adjusted deep learning model.

5. The method according to claim 1, characterized in that: The step of determining the prediction result event corresponding to the target urban rail transit train according to the plurality of driving events includes: Obtaining a first data table, wherein the first data table records a plurality of first driving event sets and result events corresponding to each of the first driving event sets; Matching the multiple driving events included in the target driving log with the multiple driving events included in each of the first driving event sets; The result event corresponding to the first driving event set that is successfully matched is determined as the predicted result event corresponding to the target urban rail transit train.

6. The method according to claim 1, characterized in that The method further comprises: Obtain a second data table, wherein the second data table records a plurality of second driving event sets and a solution corresponding to each of the second driving event sets; Matching the multiple driving events included in the target driving log with the multiple driving events included in each of the second driving event sets; Determine the solution corresponding to the successfully matched second driving event set as the solution corresponding to the target urban rail transit train; The output displays a plurality of the driving events, the safety analysis results corresponding to each of the driving events, and the prediction result events corresponding to the target urban rail transit train, including: The output displays a plurality of the driving events, the safety analysis results corresponding to each of the driving events, and the prediction result events and solutions corresponding to the target urban rail transit trains.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The plurality of driving events and the safety analysis result corresponding to each of the driving events are sent to a target terminal device, so that the target terminal device outputs and displays the plurality of driving events and the safety analysis result corresponding to each of the driving events.

8. A driving log safety analysis device, characterized in that: The device comprises: An acquisition unit, used to acquire a target driving log corresponding to a target city rail transit train, wherein the target driving log is a driving log collected by an onboard system of the target city rail transit train when the target city rail transit train is traveling on the target city rail transit line in a backup mode; A first determining unit is used to determine a plurality of driving events included in the target driving log, and to perform safety analysis on the plurality of driving events to obtain a safety analysis result corresponding to each of the driving events, wherein the safety analysis result corresponding to the driving event is used to indicate whether the driving event brings a safety risk to the driving of the target urban rail transit train; A second determining unit is used to determine a prediction result event corresponding to the target urban rail transit train according to the plurality of driving events, wherein the prediction result event is used to indicate whether the target urban rail transit train has a safety risk in a future period of time; The output unit is used to output and display multiple driving events, the safety analysis results corresponding to each driving event, and the predicted result events corresponding to the target city rail transit train, so that the train driver of the target city rail transit train can know whether the target city rail transit train has performed operations with safety risks while driving in the target city rail transit line in a backup mode, and whether the target city rail transit train will have safety risks in the future.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the driving log safety analysis method according to any one of claims 1 to 7.

10. A driving log safety analysis device, characterized in that: The device includes a storage medium; and one or more processors, the storage medium is coupled to the processor, and the processor is configured to execute program instructions stored in the storage medium; when the program instructions are executed, the driving log safety analysis method described in any one of claims 1 to 7 is executed.

Images